The Impact of Learning Analytics on Student Performance and Satisfaction in a Higher Education Course
Abstract: Learning analytics (LA) is collecting, processing, and visualization of big data to optimize learning. This article aims to interpret the impact of analyzing learning data for tertiary education. The article describes a semester-long mixed methods study for 63 students enrolled in a Greek technical university laboratory, retrieving data from the learning management system (LMS). We applied minimal LA guidance in the experimental group and no LA guidance in the control group. The research questions are as follows: Can a student-facing learning analytics approach at minimal level guidance improve students' LMS access and learning performance levels? Are the students' LMS access, discussion forums, and submitted assignments, critical predictors for students' course grades? What are students' opinions about learning analytics as a tool for data-driven decision-making strategy? The study followed the do-analyze-change-reflect LA model. The data collected included students' time spent on LMS, exercises, and discussion posts, while the dependent variable was the course grade. Results indicate that it increased the students' LMS access and satisfaction when we applied LA but not their final grade. Future research could apply higher effort interventions and stronger teacher guidance to provide insights into student performance, engagement, self-reflection, and satisfaction.